A method for identifying abnormal tire wear by analyzing tire tread color difference

Abstract

This invention relates to the field of tire manufacturing technology, and more particularly to a method for identifying abnormal tire wear through tread color difference in automobile tires. The method includes: determining scanning parameters; correcting the scanning parameters; acquiring a point cloud map; selecting quantization parameters and training a wear state model based on historical detection data; establishing a mapping relationship; acquiring quantization parameter values ​​of the automobile tire based on the detection data of the tire under test and the wear state model; generating a quantization parameter point cloud map; verifying the accuracy of the quantization parameter values ​​based on the spectrum of reflected light and the quantization parameter point cloud map; and generating a visualized quantization parameter point cloud map. This invention dynamically corrects the scanning parameters based on the actual circumference to ensure accurate point cloud data, combines a machine learning model to automatically calculate quantization parameters, and finally transforms abstract wear data into intuitive visual images through color mapping, thereby directly obtaining the wear condition by observing color, improving the detection efficiency for abnormal tire wear.

Description

Technical Field

[0001] This invention relates to the field of tire manufacturing technology, and in particular to a method for identifying abnormal tire wear by measuring the color difference of the tire tread. Background Technology

[0002] As the only part of a vehicle in contact with the road, the wear and tear of car tires directly affects driving safety, handling, and fuel economy. Statistics show that over 30% of traffic accidents are related to abnormal tire wear; therefore, tire wear inspection is a core part of vehicle maintenance.

[0003] Existing tire wear detection methods are mainly divided into three categories: Manual inspection: This relies on repair personnel visually observing tread depth and wear uniformity, or using simple calipers to measure local parameters. This method is heavily influenced by subjective experience, has low accuracy, and is difficult to meet the needs of large-scale testing. Contact instrument inspection: This uses tools such as tread depth gauges and wear gauges to measure the tire tread. While it can obtain local quantitative data, it requires point-by-point operation, has a limited detection range, and mechanical contact may scratch the tire tread rubber, making it particularly unsuitable for high-performance tires or run-flat tires. Non-contact technologies: These include laser scanning and machine vision. Laser scanning can obtain a three-dimensional point cloud of the tire tread, but existing technologies mostly focus only on geometric parameters and do not consider color differences caused by wear. While machine vision can capture color differences, it is greatly affected by lighting conditions and lacks integration with three-dimensional spatial coordinates, making it difficult to accurately quantify the degree of wear.

[0004] Therefore, existing technologies have shortcomings in achieving high-precision quantitative detection and intuitive visualization of tire wear, as well as in establishing the correlation between wear level and tread color difference, and urgently need improvement. Summary of the Invention

[0005] The purpose of this invention is to provide a method for identifying abnormal tire wear by means of tire tread color difference, so as to solve the problem that the existing technology has deficiencies in achieving high-precision quantitative detection and intuitive visualization of tire wear, and in establishing the correlation between wear degree and tread color difference.

[0006] This invention provides a method for identifying abnormal tire wear by measuring tread color difference in automobile tires, comprising:

[0007] The point cloud density is determined based on standard tire parameters and actual accuracy requirements, and the scanning parameters are determined based on the point cloud density.

[0008] The tire to be tested is placed on a fixed device, and the actual circumference of the tire is collected. The scanning parameters are then corrected based on the actual circumference.

[0009] The rotating fixing device is used to scan the tire tread to obtain a point cloud map containing spatial coordinates;

[0010] Quantitative parameters for automobile tire wear are selected, and historical detection data based on these parameters are obtained. A wear state model is then trained based on the dataset.

[0011] Establish a mapping relationship between the numerical range of the quantization parameter and a specific color in a predefined color space;

[0012] The tire under test is scanned and detected to obtain detection data. Based on the detection data and the wear state model, the quantitative parameter values ​​of the tire under test are obtained.

[0013] The point cloud map is matched with the quantization parameter value to generate a quantization parameter point cloud map;

[0014] The spectrum of the reflected light is matched with the point cloud map of the quantization parameters, and the accuracy of the quantization parameter values ​​is verified based on the matching results.

[0015] In response to the accuracy of the quantization parameter value, the quantization parameter point cloud is rendered according to the mapping relationship to generate a visualized quantization parameter point cloud.

[0016] As a preferred technical solution for identifying abnormal tire wear by means of color difference in the tire tread, the scanning parameters include: laser scanning line frequency and scanning speed.

[0017] As a preferred technical solution for identifying abnormal tire wear by means of tire tread color difference, the scanning parameters are corrected based on the actual circumference of the tire to be tested. The maximum outer diameter of the tire cross section is measured by a laser rangefinder and the actual circumference of the tire to be tested is calculated. Based on the ratio of the measured circumference to the standard circumference, the point cloud coordinates are radially scaled and corrected. The scanning parameters are then corrected based on the corrected point cloud coordinates.

[0018] As a preferred technical solution for a method of identifying abnormal tire wear through tire tread color difference, the radial scaling correction specifically includes:

[0019] Establish a cylindrical coordinate system with the tire rotation axis as the origin, and convert the Cartesian coordinates of the point cloud into polar coordinates;

[0020] Based on the ratio coefficient between the measured perimeter and the standard perimeter, the radial coordinate values ​​are scaled proportionally.

[0021] The corrected polar coordinates are then converted back to Cartesian coordinate system point cloud.

[0022] As a preferred technical solution for identifying abnormal tire wear through tire tread color difference, the step of correcting the scanning parameters based on the corrected point cloud coordinates includes: proportionally correcting the scanning speed according to the ratio between the actual circumference and the standard circumference, and correcting the laser scanning line emission frequency according to the corrected scanning speed and the preset point cloud density requirements.

[0023] As a preferred technical solution for identifying abnormal tire wear by means of tire tread color difference, the quantitative parameter is any one of wear depth, shoulder height difference, surface roughness, groove residue rate or abnormal wear area.

[0024] As a preferred technical solution for identifying abnormal tire wear through tire tread color difference, the wear state model is built using the relationship between the propagation parameters of reflected light and the quantization parameter values ​​as input data. If the propagation parameters are input, the quantization parameter values ​​are output.

[0025] The propagation parameters include: the intensity of the reflected light and the propagation time of the laser from emission to return;

[0026] The detection data refers to data generated from the propagation parameters of the reflected light.

[0027] As a preferred technical solution for a method of identifying abnormal tire wear through tire tread color difference, the step of matching the spectral map of reflected light with the point cloud map of quantized parameters, and verifying the accuracy of the quantized parameter values ​​based on the matching results, includes:

[0028] The tire wear condition is determined based on the quantified parameter values;

[0029] The spectrum of reflected light and the spectral absorption characteristics of tire rubber are obtained to determine the relative wear state of each point cloud map of the tire.

[0030] The relative wear state is compared with the quantization parameter value. If the relative wear state and the quantization parameter value do not match, the detection result is determined to be abnormal, the quantization parameter is replaced and the test is repeated.

[0031] The detection result is determined to be normal if the relative wear state matches the quantization parameter value.

[0032] As a preferred technical solution for identifying abnormal tire wear through tire tread color difference, after acquiring the point cloud image, a point cloud preprocessing step is also included, in which scanning noise points are removed by a bilateral filtering algorithm, the point cloud normal vector is calculated by principal component analysis, and the point cloud orientation deviation is corrected based on the normal vector direction.

[0033] As a preferred technical solution for identifying abnormal tire wear through tire tread color difference, the predefined color space is the Lab color space, and the establishment of the mapping relationship includes: mapping the minimum value of the quantization parameter to the dark blue of L=20, a=0, b=0 in the Lab space, mapping the maximum value to the orange-red of L=90, a=50, b=50, and the intermediate value to the transition color in the Lab space through linear interpolation.

[0034] Compared with existing technologies, the beneficial effects of this invention are that it establishes a mapping relationship between quantitative parameters and the Lab color space, transforming abstract wear data into an intuitive color distribution that gradually changes from dark blue to orange-red, corresponding one-to-one with the degree of wear from light to dark. This allows operators to quickly locate abnormal wear areas and determine the severity of wear simply by observing the color differences in the visualized point cloud map, without requiring specialized knowledge. This direct mapping of "color difference - wear" allows operators to directly obtain wear information by observing color, improving the efficiency of detecting abnormal tire wear.

[0035] Furthermore, this invention ensures the high accuracy and integrity of point cloud data by dynamically adjusting scanning parameters, correcting point cloud coordinates, and optimizing preprocessing, laying a reliable foundation for the extraction of wear quantification parameters. Based on the wear state model trained on historical data, it achieves a precise correlation between reflected light parameters and wear degree, controlling the detection error of quantification parameters (such as wear depth, surface roughness, etc.) within ±0.05mm, which is more than 10 times more accurate than traditional manual detection, effectively avoiding the omission of hidden wear. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating the steps of a method for identifying abnormal tire wear based on tread color difference, as described in an embodiment of the present invention. Detailed Implementation

[0037] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0038] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0039] Please see Figure 1 The diagram shown is a flowchart illustrating the steps of a method for identifying abnormal tire wear based on tread color difference according to an embodiment of the present invention, including:

[0040] Step S1: Determine the point cloud density based on standard tire parameters and actual accuracy requirements, and determine the scanning parameters based on the point cloud density.

[0041] Step S2: Place the tire to be tested on the fixed device, collect the actual circumference of the tire to be tested, and correct the scanning parameters based on the actual circumference;

[0042] Step S3: Rotate the fixing device and scan the tire tread to obtain a point cloud map containing spatial coordinates;

[0043] Step S4: Select quantitative parameters for tire wear and obtain historical detection data based on the quantitative parameters; train a wear state model based on the dataset.

[0044] Step S5: Establish the mapping relationship between the numerical range of the quantization parameters and specific colors in the predefined color space;

[0045] Step S6: Scan the tire to be tested to obtain test data. Based on the test data and the wear state model, obtain the quantitative parameter values ​​of the tire to be tested.

[0046] Step S7: Match the point cloud map with the quantization parameter values ​​to generate a quantization parameter point cloud map;

[0047] Step S8: Match the spectrum of the reflected light with the point cloud map of the quantization parameters, and verify the accuracy of the quantization parameter values ​​based on the matching results.

[0048] Step S9: In response to the accurate quantization parameter values, the quantization parameter point cloud is rendered according to the mapping relationship to generate a visualized quantization parameter point cloud.

[0049] In implementation, the point cloud density is determined based on standard tire parameters and actual accuracy requirements. The scanning parameters are then determined based on the point cloud density. Referring to the diameter (e.g., 19 inches) and width (e.g., 235 mm) of the standard tire, and considering the actual detection accuracy requirements (e.g., error ≤ 0.1 mm), the point cloud density is set to 60 points per square centimeter. Based on this, the initial scanning parameters are set to a laser power of 5 mW and a scanning line frequency of 800 Hz. This process is based on existing technology and will not be elaborated further here.

[0050] In detail, this invention collects the circumference of a standard tire and dynamically corrects the scanning parameters based on the actual circumference to ensure the accuracy of the point cloud data. Combined with a machine learning model, it realizes the automatic calculation of quantitative parameters. Finally, through color mapping, it transforms the abstract wear data into an intuitive visual image. By mapping the relationship between color difference and wear, operators can directly obtain the wear condition by observing the color, thus improving the detection efficiency of abnormal tire wear.

[0051] Furthermore, the scanning parameters include:

[0052] The laser scanning line frequency, which is the number of scanning lines emitted by the laser emitter per unit time (e.g., 500Hz means 500 scanning lines are emitted per second), determines the lateral density of the point cloud.

[0053] Scanning speed, i.e., the speed at which the tire tread moves relative to the scanner when the tire is rotating (e.g., 10 mm / s), affects the longitudinal density of the point cloud.

[0054] In detail, this invention matches the laser scanning line frequency and scanning speed with the tire to ensure uniform point cloud data density for tires of different sizes. On the one hand, it avoids the loss of details or the increased computational load caused by data sparsity or data redundancy. On the other hand, it eliminates the blurring of wear boundaries caused by point cloud sparsity, providing a stable data foundation for subsequent quantitative analysis. It ensures that the red-blue transition band in the color difference image is sharp and clear, allowing inspectors to determine the boundary without image magnification. This facilitates subsequent inspectors to directly obtain the wear condition by observing the color, thereby further improving the detection efficiency for abnormal tire wear.

[0055] Furthermore, the scanning parameters are corrected based on the actual circumference of the tire under test. The maximum outer diameter of the tire cross section is measured by a laser rangefinder and the actual circumference of the tire under test is calculated. Based on the ratio of the measured circumference to the standard circumference, the point cloud coordinates are radially scaled and corrected. The scanning parameters are then corrected based on the corrected point cloud coordinates.

[0056] In practice, for worn tires, the outer diameter of the cross-section is measured using a laser rangefinder (e.g., actual measurement 620mm, standard 650mm). The tire curve is collected and integrated to calculate the actual circumference ≈ 1948mm, and the standard circumference = π × 650 ≈ 2042mm, with a ratio of 1948 / 2042 ≈ 0.954 (due to the reduction in circumference caused by wear). Based on this ratio, the original point cloud is radially scaled and corrected: the radial coordinates (distance from the rotation axis) of the point cloud are uniformly multiplied by 0.954 (e.g., the original radial distance is 325mm, and after correction 325 × 0.954 ≈ 310mm) to ensure that the point cloud is consistent with the size of the worn tire. The scanning parameters are simultaneously corrected: the original scanning speed of 12mm / s is corrected to 12 × 0.954 ≈ 11.45mm / s to ensure that the tread length scanned per unit time matches the required point cloud density.

[0057] Furthermore, this invention addresses the reduction in circumference caused by wear by proportionally correcting the point cloud coordinates and scanning parameters, eliminating the influence of dimensional deviations on detection. This allows the point cloud data to accurately reflect the actual contour of the tire after wear, providing a reliable benchmark for quantitative analysis. It also facilitates subsequent inspection personnel to intuitively obtain the wear condition through the mapping of color difference and wear, thereby further improving the detection efficiency for abnormal tire wear.

[0058] Specifically, the radial scaling correction includes:

[0059] Establish a cylindrical coordinate system with the tire rotation axis as the origin, and convert the Cartesian coordinates of the point cloud into polar coordinates;

[0060] Based on the ratio coefficient between the measured perimeter and the standard perimeter, the radial coordinate values ​​are scaled proportionally.

[0061] The corrected polar coordinates are then converted back to Cartesian coordinate system point cloud.

[0062] Furthermore, this invention uses radial scaling correction to ensure that the point cloud accurately corresponds to the tire size after wear, avoiding spatial coordinate deviations caused by reduced circumference. This ensures accurate calculation of wear location and degree, providing a foundation for subsequent accurate mapping of color difference and wear relationship. It also allows subsequent inspection personnel to intuitively obtain wear information through the mapping of color difference and wear relationship, thereby further improving the detection efficiency for abnormal tire wear.

[0063] Furthermore, the scanning parameters are corrected based on the corrected point cloud coordinates, including: adjusting the scanning speed proportionally according to the ratio between the actual circumference and the standard circumference, so that the scanning speed and the adjusted rotational step angular velocity change synchronously, ensuring that the ratio of the tread arc length scanned per unit time remains unchanged; and dynamically increasing or decreasing the laser scanning line emission frequency according to the corrected scanning speed and the preset point cloud density requirements, so as to ensure that the number of point clouds acquired per unit area of ​​the tread remains constant.

[0064] In practice, if the actual measured circumference is 2000mm, the standard circumference is 2100mm, and the original scanning speed is 800mm / s, then the ratio k=0.95, which will be corrected to 800×0.95=760mm / s.

[0065] Laser frequency correction: If the preset point cloud density is 2 points / mm, then the corrected frequency = scanning speed × point cloud density = 760 × 2 = 1520Hz (original frequency 1600Hz). The frequency parameters are updated in real time through the laser controller.

[0066] Furthermore, by reasonably adjusting the scanning speed and frequency, this invention maintains a constant point cloud density, avoiding stripe artifacts in the color difference map caused by speed changes. This ensures that high-quality point cloud data can be acquired under various tire sizes and wear conditions, providing a foundation for accurate mapping of the relationship between color difference and wear. This allows subsequent inspection personnel to intuitively obtain the wear condition through the mapping of the relationship between color difference and wear, thereby further improving the detection efficiency for abnormal tire wear.

[0067] Furthermore, the quantization parameters include:

[0068] Wear depth, which is the vertical distance from the bottom of the tread groove to the worn surface, is measured by a laser displacement sensor to measure the height difference between a point on the tread and the standard tread, with an accuracy of ±0.02mm and a range of 0-5mm.

[0069] Shoulder height difference, i.e. the average height deviation between the tire shoulder area and the center area, extract the point cloud of the tire shoulder (50mm from the tire sidewall), and calculate the Z coordinate difference between the highest and lowest points, ranging from 0-3mm;

[0070] Surface roughness, which is the microscopic unevenness calculated by the variance of the point cloud normal vector, is calculated by the intensity distribution of reflected light and is represented by the Ra value (0.5-5μm). The greater the roughness, the more dispersed the reflected light.

[0071] Trench residual rate, which is the percentage of the actual depth of the trench to the designed depth;

[0072] Abnormal wear area refers to the area of ​​a continuous region that exceeds the preset wear threshold.

[0073] Furthermore, in this embodiment of the invention, wear depth is selected as a quantification parameter.

[0074] Specifically, this invention achieves visual differentiation of different wear types through color mapping of multi-dimensional quantitative parameters. For example, uneven wear is represented by a single-sided orange-red color, while groove wear is represented by dark stripes. This allows operators to quickly identify wear types based on color type and distribution, improving the efficiency of detecting abnormal tire wear.

[0075] Furthermore, the wear state model is built using the relationship between the propagation parameters of reflected light and the quantization parameter values ​​as input data. If the propagation parameters are input, the quantization parameter values ​​are output.

[0076] Propagation parameters include: reflected light intensity and the propagation time of the laser from emission to return;

[0077] The detection data consists of data generated from the propagation parameters of the reflected light.

[0078] In implementation, a ToF camera was used to simultaneously acquire the reflected light intensity (0-255) and propagation time (0-100ns) on the tire surface, with each set of data corresponding to one point cloud coordinate. A dataset was constructed, with the reflected light intensity and propagation time as inputs and the wear depth as the output.

[0079] Furthermore, this invention achieves non-contact quantitative detection through a wear state model of reflected light parameters, avoiding damage to the tire caused by mechanical measurement. By mapping the relationship between color difference and wear, operators can directly obtain the wear condition by observing the color, thus improving the detection efficiency for abnormal tire wear.

[0080] Furthermore, the accuracy of the quantization parameter values ​​is verified based on the spectrum of the reflected light and the matching results of the quantization parameter values, including:

[0081] The tire wear condition is determined based on the quantified parameter values;

[0082] The spectrum of reflected light and the spectral absorption characteristics of tire rubber are obtained to determine the relative wear state of each point cloud map of the tire.

[0083] The relative wear state is compared with the quantization parameter value. If the relative wear state and the quantization parameter value do not match, the detection result is determined to be abnormal, the quantization parameter is replaced and the test is repeated.

[0084] The detection result is determined to be normal if the relative wear state matches the quantization parameter value.

[0085] Furthermore, assuming there are four point clouds A, B, C, and D, the spectral absorption characteristics of tire rubber are as follows: as the degree of oxidation increases, the degree of redshift in the ultraviolet-visible region gradually increases; based on the measured quantitative parameter values, it is known that the wear degree values ​​corresponding to the four point clouds A, B, C, and D, from low to high, are A, C, D, and B, respectively.

[0086] Now, each of the four point clouds A, B, C, and D corresponds to a spectral map, denoted as a, b, c, and d, respectively. The degree of redshift in the ultraviolet-visible region absorption is compared among a, b, c, and d.

[0087] The first scenario: If the four point clouds A, B, C, and D are sorted according to the order of the redshift of the UV-Vis absorption in the UV-Vis region from low to high, the order is A, C, D, B. Combining this with the spectral absorption characteristics of tire rubber, the oxidation degree from low to high is A, C, D, B, which means the wear degree from low to high is A, C, D, B. In other words, the relative wear state matches the quantification parameter value, and the detection result is normal.

[0088] The second scenario: If the four point clouds A, B, C, and D are sorted according to the order of the redshift of the UV-Vis absorption in a, b, c, and d from low to high, the order would be A, B, C, and D. Combining this with the spectral absorption characteristics of tire rubber, the oxidation degree from low to high is A, B, C, and D, which means the wear degree from low to high is A, B, C, and D. In other words, the relative wear state does not match the quantification parameter value, and the detection result is abnormal.

[0089] Due to varying contact times with air, the fresh and aged surfaces of the rubber exposed in the wear zone exhibit spectral differences. For low oxidation states, the characteristic peaks of the rubber's carbon chains and double bonds dominate, while oxygen-containing functional group peaks are weak. For high oxidation states, oxygen-containing functional group peaks (especially carbonyl groups) are significantly enhanced, while the original carbon chain / double bond peaks weaken or deform. Changes in the conjugated system may lead to a redshift in the UV-Vis absorption region. Furthermore, since a new rubber surface is created after wear, its contact time with air differs from the original surface, resulting in varying degrees of spectral impact. Combining this difference with the coordinates of each point cloud generates a relative wear state of each point cloud coordinate relative to other point cloud coordinates. Comparing the values ​​of quantified parameters also yields a wear state of each cloud point relative to other cloud points. If these two wear states do not match, the detection results are inaccurate. Therefore, the monitoring results are validated based on the spectrum, thereby increasing the accuracy of the detection results for abnormal tire wear.

[0090] Furthermore, after acquiring the point cloud image, a point cloud preprocessing step is also included, in which scanning noise points are removed by a bilateral filtering algorithm, the point cloud normal vector is calculated by principal component analysis, and the point cloud orientation deviation is corrected based on the direction of the normal vector.

[0091] In practice, principal component analysis is used to calculate the normal vector of each point. Points with an angle greater than 10° with the tire radial direction are rotated and corrected to ensure that the normal vectors consistently point to the outer side of the tire tread.

[0092] Specifically, this invention preprocesses the point cloud image to avoid "false color" interference caused by noise points and color misalignment caused by directional deviation, making the wear area easier to identify. By mapping the relationship between color difference and wear, operators can directly obtain the wear condition by observing the color, thus improving the detection efficiency for abnormal tire wear.

[0093] Furthermore, the predefined color space is the Lab color space. The mapping relationship is established by mapping the minimum value of the quantization parameter to the deep blue in the Lab space with L=20, a=0, b=0, the maximum value to the orange-red with L=90, a=50, b=50, and the intermediate values ​​to the transition colors in the Lab space through linear interpolation.

[0094] Specifically, this invention establishes a linear mapping in the Lab color space that positively correlates wear level with color (gradual transition from dark blue to orange-red), aligning with human color perception. Operators require no specialized training; they can determine the severity of wear simply by observing color depth. Through the mapping between color difference and wear, operators can directly assess wear by observing color, thus improving the efficiency of detecting abnormal tire wear.

[0095] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying abnormal tire wear by measuring tread color difference, characterized in that, include: The point cloud density is determined based on standard tire parameters and actual accuracy requirements, and the scanning parameters are determined based on the point cloud density. The tire to be tested is placed on a fixed device, and the actual circumference of the tire is collected. The scanning parameters are then corrected based on the actual circumference. The rotating fixing device is used to scan the tire tread to obtain a point cloud map containing spatial coordinates; Quantitative parameters for automobile tire wear are selected, and historical detection data based on these parameters are obtained. A wear state model is then trained based on the dataset. Establish a mapping relationship between the numerical range of the quantization parameter and a specific color in a predefined color space; The tire under test is scanned and detected to obtain detection data. Based on the detection data and the wear state model, the quantitative parameter values ​​of the tire under test are obtained. The point cloud map is matched with the quantization parameter value to generate a quantization parameter point cloud map; The spectrum of the reflected light is matched with the point cloud map of the quantization parameters, and the accuracy of the quantization parameter values ​​is verified based on the matching results. In response to the accuracy of the quantization parameter value, the quantization parameter point cloud is rendered according to the mapping relationship to generate a visualized quantization parameter point cloud.

2. The method for identifying abnormal tire wear by measuring tread color difference according to claim 1, characterized in that, The scanning parameters include: laser scanning line frequency and scanning speed.

3. The method for identifying abnormal tire wear by means of tread color difference according to claim 2, characterized in that, The scanning parameters are corrected based on the actual circumference. The maximum outer diameter of the tire cross section is measured by a laser rangefinder and the actual circumference of the tire to be tested is calculated. Based on the ratio of the measured circumference to the standard circumference, the point cloud coordinates are radially scaled and corrected. The scanning parameters are then corrected based on the corrected point cloud coordinates.

4. The method for identifying abnormal tire wear by means of tread color difference according to claim 3, characterized in that, The radial scaling correction specifically includes: Establish a cylindrical coordinate system with the tire rotation axis as the origin, and convert the Cartesian coordinates of the point cloud into polar coordinates; Based on the ratio coefficient between the measured perimeter and the standard perimeter, the radial coordinate values ​​are scaled proportionally. The corrected polar coordinates are then converted back to Cartesian coordinate system point cloud.

5. The method for identifying abnormal tire wear by means of tread color difference according to claim 4, characterized in that, The step of correcting the scanning parameters based on the corrected point cloud coordinates includes: Based on the ratio between the actual perimeter and the standard perimeter, the scanning speed is adjusted proportionally. Based on the adjusted scanning speed and the preset point cloud density requirements, the laser scanning line emission frequency is adjusted.

6. The method for identifying abnormal tire wear by means of tread color difference according to claim 1, characterized in that, The quantification parameter is any one of wear depth, shoulder height difference, surface roughness, groove residue rate, or abnormal wear area.

7. The method for identifying abnormal tire wear by means of tread color difference according to claim 1, characterized in that, The wear state model is built using the relationship between the propagation parameters and quantization parameter values ​​of reflected light as input data. If the propagation parameters are input, the quantization parameter values ​​are output. The propagation parameters include: the intensity of the reflected light and the propagation time of the laser from emission to return; The detection data refers to data generated from the propagation parameters of the reflected light.

8. The method for identifying abnormal tire wear by means of tread color difference according to claim 7, characterized in that, The step of matching the spectrum of the reflected light with the point cloud map of the quantization parameters, and verifying the accuracy of the quantization parameter values ​​based on the matching results, includes: The tire wear condition is determined based on the quantified parameter values; The spectrum of reflected light and the spectral absorption characteristics of tire rubber are obtained to determine the relative wear state of each point cloud map of the tire. The relative wear state is compared with the quantization parameter value. If the relative wear state and the quantization parameter value do not match, the detection result is determined to be abnormal, the quantization parameter is replaced and the test is repeated. The detection result is determined to be normal if the relative wear state matches the quantization parameter value.

9. The method for identifying abnormal tire wear by means of tread color difference according to claim 1, characterized in that, After acquiring the point cloud image, a point cloud preprocessing step is also included, in which scanning noise points are removed by a bilateral filtering algorithm, the point cloud normal vector is calculated by principal component analysis, and the point cloud orientation deviation is corrected based on the direction of the normal vector.

10. The method for identifying abnormal tire wear by means of tread color difference according to claim 1, characterized in that, The predefined color space is the Lab color space. The establishment of the mapping relationship includes: mapping the minimum value of the quantization parameter to the dark blue in the Lab space with L=20, a=0, b=0, mapping the maximum value to the orange-red with L=90, a=50, b=50, and the intermediate value to the transition color in the Lab space through linear interpolation.

Images